A Machine Learning-Sentiment Analysis on Monkeypox Outbreak: An Extensive Dataset to Show the Polarity of Public Opinion From Twitter Tweets

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 11811 - 11826

Published: Jan. 1, 2023

Research on sentiment analysis has proven to be very useful in public health, particularly analyzing infectious diseases. As the world recovers from onslaught of COVID-19 pandemic, concerns are rising that another known as monkeypox, might hit again. Monkeypox is an disease reported over 73 countries across globe. This sudden outbreak become a major concern for many individuals and health authorities. Different social media channels have presented discussions, views, opinions, emotions about monkeypox outbreak. Social sentiments often result panic, misinformation, stigmatization some minority groups. Therefore, accurate information, guidelines, protocols related this virus critical. We aim analyze recent outbreak, with purpose helping decision-makers gain better understanding perceptions disease. hope government authorities will find work crafting policies mitigating strategies control spread disease, guide against its misrepresentations. Our study was conducted two stages. In first stage, we collected 500,000 multilingual tweets post Twitter then performed them using VADER TextBlob, annotate extracted into positive, negative, neutral sentiments. The second stage our involved design, development, evaluation 56 classification models. Stemming lemmatization techniques were used vocabulary normalization. Vectorization based CountVectorizer TF-IDF methodologies. K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Random Forest, Logistic Regression, Multilayer Perceptron (MLP), Naïve Bayes, XGBoost deployed learning algorithms. Performance accuracy, F1 Score, Precision, Recall. experimental results showed model developed TextBlob annotation + Lemmatization SVM yielded highest accuracy 0.9348.

Language: Английский

---

Recent advancements and challenges of NLP-based sentiment analysis: A state-of-the-art review

Natural Language Processing Journal, Journal Year: 2024, Volume and Issue: 6, P. 100059 - 100059

Published: Feb. 29, 2024

Sentiment analysis is a method within natural language processing that evaluates and identifies the emotional tone or mood conveyed in textual data. Scrutinizing words phrases categorizes them into positive, negative, neutral sentiments. The significance of sentiment lies its capacity to derive valuable insights from extensive data, empowering businesses grasp customer sentiments, make informed choices, enhance their offerings. For further advancement analysis, gaining deep understanding algorithms, applications, current performance, challenges imperative. Therefore, this survey, we began exploring vast array application domains for scrutinizing context existing research. We then delved prevalent pre-processing techniques, datasets, evaluation metrics comprehension. also explored Machine Learning, Deep Large Language Models Pre-trained models providing advantages drawbacks. Subsequently, precisely reviewed experimental results limitations recent state-of-the-art articles. Finally, discussed diverse encountered proposed future research directions mitigate these concerns. This review provides complete covering models, domains, challenges, directions.

Language: Английский

---

Blockchain-Federated and Deep-Learning-Based Ensembling of Capsule Network with Incremental Extreme Learning Machines for Classification of COVID-19 Using CT Scans

Bioengineering, Journal Year: 2023, Volume and Issue: 10(2), P. 203 - 203

Published: Feb. 3, 2023

Due to the rapid rate of SARS-CoV-2 dissemination, a conversant and effective strategy must be employed isolate COVID-19. When it comes determining identity COVID-19, one most significant obstacles that researchers overcome is propagation virus, in addition dearth trustworthy testing models. This problem continues difficult for clinicians deal with. The use AI image processing has made formerly insurmountable challenge finding COVID-19 situations more manageable. In real world, there handled about difficulties sharing data between hospitals while still honoring privacy concerns organizations. training global deep learning (DL) model, crucial handle fundamental such as user collaborative model development. For this study, novel framework designed compiles information from five different databases (several hospitals) edifies using blockchain-based federated (FL). validated through blockchain technology (BCT), FL trains on scale maintaining secrecy proposed divided into three parts. First, we provide method normalization can diversity collected sources several computed tomography (CT) scanners. Second, categorize patients, ensemble capsule network (CapsNet) with incremental extreme machines (IELMs). Thirdly, interactively BCT anonymity. Extensive tests employing chest CT scans comparison classification performance DL algorithms predicting protecting variety users, were undertaken. Our findings indicate improved effectiveness identifying patients achieved an accuracy 98.99%. Thus, our provides substantial aid medical practitioners their diagnosis

Language: Английский

---

An efficient model for sentiment analysis using artificial rabbits optimized vector functional link network

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 225, P. 119849 - 119849

Published: March 11, 2023

Language: Английский

---

Text Mining and Emotion Classification on Monkeypox Twitter Dataset: A Deep Learning-Natural Language Processing (NLP) Approach

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 49882 - 49894

Published: Jan. 1, 2023

Emotion classification has become a valuable tool in analyzing text and emotions people express response to events or crises, particularly on social media other online platforms. The recent news about monkeypox highlighted various individuals felt during the outbreak. People's opinions concerns have been very different based their awareness understanding of disease. Although there studies monkeypox, emotion related this virus not considered. As result, study aims analyze individual expressed posts Our goal is provide real-time information identify critical To conduct our analysis, first, we extract preprocess 800,000 datasets then use NRCLexicon, Python library, predict measure emotional significance each text. Secondly, develop deep learning models Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Bi-directional LSTM (BiLSTM), combination (CLSTM) for classification. We SMOTE (Synthetic Minority Oversampling Technique) Random Undersampling techniques address class imbalance training dataset. results revealed that CNN model achieved highest performance with an accuracy 96%. Overall, dataset can be powerful improving findings will help effective interventions improve public health.

Language: Английский

---

Research on Sentiment Analysis of Online Public Opinion Based on RoBERTa–BiLSTM–Attention Model

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(4), P. 2148 - 2148

Published: Feb. 18, 2025

Public opinion comments are important for the public to express their emotions and demands. Accordingly, identifying contained in taking corresponding countermeasures according changes of great theoretical practical significance online management. This study took a event at college as an example. Firstly, microblogs comment data related were crawled with Python coding, pre-processing operations such cleaning, word splitting, de-noising carried out; then, stage was divided into phases based on daily sound volume, Baidu index, key time points event. Secondly, sentiment analysis, supplementary dictionary constructed SO-PMI algorithm merged commonly used pre-annotate corpus; RoBERTa–BiLSTM–Attention model classify microblog comments; after that, four evaluation indexes selected ablation experiments set up verify performance model. Finally, results classification, we drew trends evolution graphs analysis. The showed that significantly improved pre-labelling accuracy. achieved 91.56%, 90.87%, 91.07%, 91.17% accuracy, precision, recall, F1-score, respectively. situation notification, expert response, regulatory dynamics, secondary will trigger significant fluctuations volume sentiment.

Language: Английский

---

Adverse Effects of COVID-19 Vaccination: Machine Learning and Statistical Approach to Identify and Classify Incidences of Morbidity and Postvaccination Reactogenicity

Healthcare, Journal Year: 2022, Volume and Issue: 11(1), P. 31 - 31

Published: Dec. 22, 2022

Good vaccine safety and reliability are essential for successfully countering infectious disease spread. A small but significant number of adverse reactions to COVID-19 vaccines have been reported. Here, we aim identify possible common factors in such enable strategies that reduce the incidence by using patient data classify characterise those at risk. We examined medical histories documenting postvaccination effects outcomes. The analyses were conducted a range statistical approaches followed series machine learning classification algorithms. In most cases, group similar features was significantly associated with poor reactions. These included prior illnesses, admission hospitals SARS-CoV-2 reinfection. indicated age, gender, taking other medications, type-2 diabetes, hypertension, allergic history heart pre-existing risk outcome. addition, long duration hospital treatments, dyspnoea, various kinds pain, headache, cough, asthenia, physical disability clinical predictors. classifiers trained also able predict patients complication-free vaccination an accuracy score above 90%. Our study identifies profiles individuals may need extra monitoring care (e.g., location access comprehensive support) negative outcomes through approaches.

Language: Английский

---

Pre-large based high utility pattern mining for transaction insertions in incremental database

Knowledge-Based Systems, Journal Year: 2023, Volume and Issue: 268, P. 110478 - 110478

Published: March 20, 2023

Language: Английский

---

Multimodal negative sentiment recognition of online public opinion on public health emergencies based on graph convolutional networks and ensemble learning

Information Processing & Management, Journal Year: 2023, Volume and Issue: 60(4), P. 103378 - 103378

Published: April 9, 2023

Language: Английский

---

Addressing bias in artificial intelligence for public health surveillance

Journal of Medical Ethics, Journal Year: 2023, Volume and Issue: 50(3), P. 190 - 194

Published: May 2, 2023

Components of artificial intelligence (AI) for analysing social big data, such as natural language processing (NLP) algorithms, have improved the timeliness and robustness health data. NLP techniques been implemented to analyse large volumes text from media platforms gain insights on disease symptoms, understand barriers care predict outbreaks. However, AI-based decisions may contain biases that could misrepresent populations, skew results or lead errors. Bias, within scope this paper, is described difference between predictive values true modelling an algorithm. Bias algorithms inaccurate healthcare outcomes exacerbate disparities when derived these biased are applied interventions. Researchers who implement must consider how bias arise. This paper explores algorithmic a result data collection, labelling algorithms. role in ensuring efforts towards combating enforced, especially drawing conclusions posts linguistically diverse. Through implementation open collaboration, auditing processes development guidelines, researchers be able reduce improve surveillance.

Language: Английский

---